DataFrame / Dataset groupBy behaviour/optimization

by

Yes, it is “smart enough“. groupBy performed on a DataFrame is not the same operation as groupBy performed on a plain RDD. In a scenario you’ve described there is no need to move raw data at all. Let’s create a small example to illustrate that:

val df = sc.parallelize(Seq(
   ("a", "foo", 1), ("a", "foo", 3), ("b", "bar", 5), ("b", "bar", 1)
)).toDF("x", "y", "z")

df.groupBy("x").agg(sum($"z")).explain

// == Physical Plan ==
// *HashAggregate(keys=[x#148], functions=[sum(cast(z#150 as bigint))])
// +- Exchange hashpartitioning(x#148, 200)
//    +- *HashAggregate(keys=[x#148], functions=[partial_sum(cast(z#150 as bigint))])
//       +- *Project [_1#144 AS x#148, _3#146 AS z#150]
//          +- *SerializeFromObject [staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, assertnotnull(input[0, scala.Tuple3, true])._1, true, false) AS _1#144, staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, assertnotnull(input[0, scala.Tuple3, true])._2, true, false) AS _2#145, assertnotnull(input[0, scala.Tuple3, true])._3 AS _3#146]
//             +- Scan ExternalRDDScan[obj#143]

As you can the first phase is a projection where only required columns are preserved. Next data is aggregated locally and finally transferred and aggregated globally. You’ll get a little bit different answer output if you use Spark <= 1.4 but general structure should be exactly the same.

Finally a DAG visualization showing that above description describes actual job:

group by and agg DAG

Similarly, Dataset.groupByKey followed by reduceGroups, contains both map-side (ObjectHashAggregate with partial_reduceaggregator) and reduce-side (ObjectHashAggregate with reduceaggregator reduction):

case class Foo(x: String, y: String, z: Int)

val ds = df.as[Foo]
ds.groupByKey(_.x).reduceGroups((x, y) => x.copy(z = x.z + y.z)).explain

// == Physical Plan ==
// ObjectHashAggregate(keys=[value#126], functions=[reduceaggregator(org.apache.spark.sql.expressions.ReduceAggregator@54d90261, Some(newInstance(class $line40.$read$$iw$$iw$Foo)), Some(class $line40.$read$$iw$$iw$Foo), Some(StructType(StructField(x,StringType,true), StructField(y,StringType,true), StructField(z,IntegerType,false))), input[0, scala.Tuple2, true]._1 AS value#128, if ((isnull(input[0, scala.Tuple2, true]._2) || None.equals)) null else named_struct(x, staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, assertnotnull(assertnotnull(input[0, scala.Tuple2, true]._2)).x, true, false) AS x#25, y, staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, assertnotnull(assertnotnull(input[0, scala.Tuple2, true]._2)).y, true, false) AS y#26, z, assertnotnull(assertnotnull(input[0, scala.Tuple2, true]._2)).z AS z#27) AS _2#129, newInstance(class scala.Tuple2), staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, assertnotnull(assertnotnull(input[0, $line40.$read$$iw$$iw$Foo, true])).x, true, false) AS x#25, staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, assertnotnull(assertnotnull(input[0, $line40.$read$$iw$$iw$Foo, true])).y, true, false) AS y#26, assertnotnull(assertnotnull(input[0, $line40.$read$$iw$$iw$Foo, true])).z AS z#27, StructField(x,StringType,true), StructField(y,StringType,true), StructField(z,IntegerType,false), true, 0, 0)])
// +- Exchange hashpartitioning(value#126, 200)
//    +- ObjectHashAggregate(keys=[value#126], functions=[partial_reduceaggregator(org.apache.spark.sql.expressions.ReduceAggregator@54d90261, Some(newInstance(class $line40.$read$$iw$$iw$Foo)), Some(class $line40.$read$$iw$$iw$Foo), Some(StructType(StructField(x,StringType,true), StructField(y,StringType,true), StructField(z,IntegerType,false))), input[0, scala.Tuple2, true]._1 AS value#128, if ((isnull(input[0, scala.Tuple2, true]._2) || None.equals)) null else named_struct(x, staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, assertnotnull(assertnotnull(input[0, scala.Tuple2, true]._2)).x, true, false) AS x#25, y, staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, assertnotnull(assertnotnull(input[0, scala.Tuple2, true]._2)).y, true, false) AS y#26, z, assertnotnull(assertnotnull(input[0, scala.Tuple2, true]._2)).z AS z#27) AS _2#129, newInstance(class scala.Tuple2), staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, assertnotnull(assertnotnull(input[0, $line40.$read$$iw$$iw$Foo, true])).x, true, false) AS x#25, staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, assertnotnull(assertnotnull(input[0, $line40.$read$$iw$$iw$Foo, true])).y, true, false) AS y#26, assertnotnull(assertnotnull(input[0, $line40.$read$$iw$$iw$Foo, true])).z AS z#27, StructField(x,StringType,true), StructField(y,StringType,true), StructField(z,IntegerType,false), true, 0, 0)])
//       +- AppendColumns <function1>, newInstance(class $line40.$read$$iw$$iw$Foo), [staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, input[0, java.lang.String, true], true, false) AS value#126]
//          +- *Project [_1#4 AS x#8, _2#5 AS y#9, _3#6 AS z#10]
//             +- *SerializeFromObject [staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, assertnotnull(input[0, scala.Tuple3, true])._1, true, false) AS _1#4, staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, assertnotnull(input[0, scala.Tuple3, true])._2, true, false) AS _2#5, assertnotnull(input[0, scala.Tuple3, true])._3 AS _3#6]
//                +- Scan ExternalRDDScan[obj#3]

groupByKey + reduceGroups

However other methods of KeyValueGroupedDataset might work similarly to RDD.groupByKey. For example mapGroups (or flatMapGroups) doesn’t use partial aggregation.

ds.groupByKey(_.x)
  .mapGroups((_, iter) => iter.reduce((x, y) => x.copy(z = x.z + y.z)))
  .explain

//== Physical Plan ==
//*SerializeFromObject [staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, assertnotnull(input[0, $line15.$read$$iw$$iw$Foo, true]).x, true, false) AS x#37, staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, assertnotnull(input[0, $line15.$read$$iw$$iw$Foo, true]).y, true, false) AS y#38, assertnotnull(input[0, $line15.$read$$iw$$iw$Foo, true]).z AS z#39]
//+- MapGroups <function2>, value#32.toString, newInstance(class $line15.$read$$iw$$iw$Foo), [value#32], [x#8, y#9, z#10], obj#36: $line15.$read$$iw$$iw$Foo
//   +- *Sort [value#32 ASC NULLS FIRST], false, 0
//      +- Exchange hashpartitioning(value#32, 200)
//         +- AppendColumns <function1>, newInstance(class $line15.$read$$iw$$iw$Foo), [staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, input[0, java.lang.String, true], true, false) AS value#32]
//            +- *Project [_1#4 AS x#8, _2#5 AS y#9, _3#6 AS z#10]
//               +- *SerializeFromObject [staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, assertnotnull(input[0, scala.Tuple3, true])._1, true, false) AS _1#4, staticinvoke(class org.apache.spark.unsafe.types.UTF8String, StringType, fromString, assertnotnull(input[0, scala.Tuple3, true])._2, true, false) AS _2#5, assertnotnull(input[0, scala.Tuple3, true])._3 AS _3#6]
//                  +- Scan ExternalRDDScan[obj#3]

groupByKey + mapGroups

More Related Contents:

  1. Spark functions vs UDF performance?
  2. Difference between DataFrame, Dataset, and RDD in Spark
  3. Difference between DataFrame, Dataset, and RDD in Spark
  4. Spark sql queries vs dataframe functions
  5. What is the difference between spark.sql.shuffle.partitions and spark.default.parallelism?
  6. How to get keys and values from MapType column in SparkSQL DataFrame
  7. Why is predicate pushdown not used in typed Dataset API (vs untyped DataFrame API)?
  8. How to pivot Spark DataFrame?
  9. Spark SQL: apply aggregate functions to a list of columns
  10. Concatenate columns in Apache Spark DataFrame
  11. How to define partitioning of DataFrame?
  12. Spark: Inconsistent performance number in scaling number of cores
  13. How do I add a new column to a Spark DataFrame (using PySpark)?
  14. Dropping a nested column from Spark DataFrame
  15. Spark Dataframe :How to add a index Column : Aka Distributed Data Index
  16. Defining a UDF that accepts an Array of objects in a Spark DataFrame?
  17. Updating a dataframe column in spark
  18. Dividing complex rows of dataframe to simple rows in Pyspark
  19. Spark Dataframes UPSERT to Postgres Table
  20. Spark add new column to dataframe with value from previous row
  21. Create new Dataframe with empty/null field values
  22. Perform a typed join in Scala with Spark Datasets
  23. Why does Spark think this is a cross / Cartesian join
  24. Pyspark: Replacing value in a column by searching a dictionary
  25. Pivot String column on Pyspark Dataframe
  26. Pyspark filter dataframe by columns of another dataframe
  27. Derive multiple columns from a single column in a Spark DataFrame
  28. Filtering DataFrame using the length of a column
  29. How to exclude multiple columns in Spark dataframe in Python
  30. Difference between === null and isNull in Spark DataDrame

Leave a Comment